VIBRATION FEATURES GENERATED WITH CONTACTOR SWITCHING USING FBG

The dataset consists of measurements of four different stages of degradation in low-voltage contactors used for industrial purposes. The measurements were obtained with fiber Bragg grating (FBG) sensors that detect the dynamic deformation generated in switching under different internal components. The measurements were processed and features from PSD, FFT and TSFEL python library were extracted. The features of PSD and FFT were acquired in 40 sliding windows of 50Hz from the signal. The first attribute presents the average of the PSD for that window, and the second attribute presents the position of the highest FFT peak of that window.  Furthermore, two sets of features were obtained, one for frequency analisys and one for TSFEL. The dataset was split into training, validation, and testing. The training and validation set has data augmentation to synthesize a larger quantity of signals of the same class, variability in the contactor fixation, variation of the FBG sensor in the same installation position, and variation of the contactor, while still being of the same model. The test set represents a dataset never seen by the training and validation, yet still being the same contactor model with an FBG installed in the same position as the other data.